The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and analyze external, user-provided legacy frontend code and stylesheets.
Ingestion points: Legacy CSS entry points, DOM structures, and functional components identified during the audit workflow described in SKILL.md.
Boundary markers: Absent. The instructions do not define specific delimiters for separating user-provided code from agent instructions.
Capability inventory: None. The skill is purely instructional and does not utilize tools for file system modification, network communication, or shell command execution.
Sanitization: Absent. There are no instructions for sanitizing or escaping the content of the legacy files being analyzed.
[SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were identified. The metadata in markets/openai-compatible.json correctly points to the author's own repository, and the instructions align with established software engineering best practices for frontend migration.

frontend-refactoring